Session

每一个Session都维护各自变量的副本。

如下所示：

W = tf.Variable(10)

sess1 = tf.Session()

sess2 = tf.Session()

sess1.run(W.initializer)

sess2.run(W.initializer)

print sess1.run(W.assign_add(10)) # >> 20

print sess2.run(W.assign_sub(2)) # >> ?

？等号8，sess1和sess2各自维护W，所以sess1中W增加10，不会影响sess2的W，所以它等于10-2=8.

Session vs InteractiveSession

有时候我们会看到：InteractiveSession，而不是Session，它们区别是？

One major change is the use of an InteractiveSession, which allows us to run variables without needing to constantly refer to the session object (less typing!). 

InteractiveSession()

sess = tf.InteractiveSession()

a = tf.constant(5.0)

b = tf.constant(6.0)

c = a * b

# We can just use 'c.eval()' without specifying the context 'sess'

print(c.eval())

sess.close()

Session()

sess = tf.Session()

a = tf.constant(5.0)

b = tf.constant(6.0)

c = a * b

with tf.Session() as sess: 

    sess.run(print(c.eval()))